© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1395
    Prev
    Next
    INDEX
    Explanations

    Option 1:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     error
    0.84
     transfer
    0.84
     bedding
    0.83
     can
    0.81
    ↵↵
    0.80
     affect
    0.79
     impact
    0.79
     stop
    0.78
     aids
    0.78
     model
    0.77
    POSITIVE LOGITS
     قال
    0.95
    Transform
    0.92
    Transforms
    0.89
    ânico
    0.87
     فونبټ
    0.87
    <unused1303>
    0.85
    ledad
    0.85
    玖章
    0.85
     Elevations
    0.85
    Insights
    0.84
    Activations Density 0.013%

    No Known Activations